Performance issues and error analysis in an open-domain question answering system

  • Authors:
  • Dan Moldovan;Marius Paşca;Sanda Harabagiu;Mihai Surdeanu

  • Affiliations:
  • Language Computer Corporation, Richardson, TX;Language Computer Corporation, Richardson, TX;Language Computer Corporation, Richardson, TX;Language Computer Corporation, Richardson, TX

  • Venue:
  • ACM Transactions on Information Systems (TOIS)
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an in-depth analysis of a state-of-the-art Question Answering system. Several scenarios are examined: (1) the performance of each module in a serial baseline system, (2) the impact of feedbacks and the insertion of a logic prover, and (3) the impact of various retrieval strategies and lexical resources. The main conclusion is that the overall performance depends on the depth of natural language processing resources and the tools used for answer finding.